Skip to content

Commit 1be4b3b

Browse files
authored
Deprecate 2x Tensorflow, Keras and ONNX (#2199)
Signed-off-by: Xin He <[email protected]>
1 parent 5cbbf72 commit 1be4b3b

File tree

156 files changed

+2255
-2203
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

156 files changed

+2255
-2203
lines changed

docs/source/adaptor.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -24,9 +24,9 @@ tuning strategy and vanilla framework quantization APIs.
2424

2525
|Framework |Adaptor |
2626
|--------------|:-----------:|
27-
|TensorFlow |&#10004; |
27+
|TensorFlow (Deprecated) |&#10004; |
2828
|PyTorch |&#10004; |
29-
|ONNX |&#10004; |
29+
|ONNX (Deprecated) |&#10004; |
3030

3131

3232
## Working Flow

docs/source/benchmark.md

Lines changed: 4 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,7 @@
1-
Benchmarking
2-
============
1+
Benchmarking (Deprecated)
2+
===============
3+
> Since version >= 3.3, this functionality has been replaced by [incbench](https://github.com/intel/neural-compressor/blob/master/docs/source/3x/benchmark.md), which is easier to use.
4+
----------------------------
35
1. [Introduction](#Introduction)
46
2. [Benchmark Support Matrix](#Benchmark-Support-Matrix)
57
3. [Get Started with Benchmark](#Get-Started-with-Benchmark)

docs/source/dataloader.md

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -31,10 +31,10 @@ Of cause, users can also use frameworks own dataloader in Neural Compressor.
3131

3232
| Framework | Status |
3333
|---------------|:----------:|
34-
| TensorFlow | &#10004; |
35-
| Keras | &#10004; |
34+
| TensorFlow (Deprecated) | &#10004; |
35+
| Keras (Deprecated) | &#10004; |
3636
| PyTorch | &#10004; |
37-
| ONNX Runtime | &#10004; |
37+
| ONNX Runtime (Deprecated) | &#10004; |
3838

3939
## Get Started with DataLoader
4040

docs/source/distillation_quantization.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -23,7 +23,7 @@ Intel provides a quantization-aware training (QAT) method that incorporates a no
2323

2424
### Distillation for Quantization Support Matrix
2525

26-
|**Algorithm** |**PyTorch** |**TensorFlow** |
26+
|**Algorithm** |**PyTorch** |**TensorFlow (Deprecated)** |
2727
|---------------------------------|:--------:|:---------:|
2828
|Distillation for Quantization |&#10004; |&#10006; |
2929

docs/source/distributed.md

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -16,7 +16,7 @@ Distributed Training and Inference (Evaluation)
1616

1717
4.1. [Pytorch Examples](#pytorch-examples)
1818

19-
4.2. [Tensorflow Examples](#tensorflow-examples)
19+
4.2. [Tensorflow Examples](#tensorflow-examples) (Deprecated)
2020
## Introduction
2121

2222
Neural Compressor uses [horovod](https://github.com/horovod/horovod) for distributed training.
@@ -33,8 +33,8 @@ Distributed training and inference are supported in PyTorch and TensorFlow curre
3333
|------------|---------|:-------------------:|
3434
| PyTorch | QAT | &#10004; |
3535
| PyTorch | PTQ | &#10004; |
36-
| TensorFlow | PTQ | &#10004; |
37-
| Keras | Pruning | &#10004; |
36+
| TensorFlow (Deprecated) | PTQ | &#10004; |
37+
| Keras (Deprecated) | Pruning | &#10004; |
3838

3939
## Get Started with Distributed Training and Inference API
4040
To enable distributed training or inference, the steps are:
@@ -168,7 +168,7 @@ Horovodrun requires user set up SSH on all hosts without any prompts. To do dist
168168
- PyTorch example-2: QAT (Quantization Aware Training)
169169
- Please follow this README.md exactly:[QAT](../../examples/pytorch/image_recognition/torchvision_models/quantization/qat/eager/distributed)
170170

171-
### TensorFlow Examples:
171+
### TensorFlow Examples: (Deprecated)
172172
- TensorFlow example-1: 'ResNet50 V1.0' PTQ (Post Training Quantization) with distributed inference
173173
- Step-1: Please cd (change directory) to the [TensorFlow Image Recognition Example](../../examples/tensorflow/image_recognition) and follow the readme to run PTQ, ensure that PTQ of 'ResNet50 V1.0' can be successfully executed.
174174
- Step-2: We only need to modify the [resnet50_v1.yaml](../../examples/tensorflow/image_recognition/tensorflow_models/quantization/ptq/resnet50_v1.yaml), add a line 'distributed: True' in the 'evaluation' field.

docs/source/export.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -48,7 +48,7 @@ Here is the workflow of our export API for PyTorch/Tensorflow FP32/INT8 model.
4848
<td>QOperator/QDQ INT8</td>
4949
</tr>
5050
<tr>
51-
<td rowspan="3">TensorFlow</td>
51+
<td rowspan="3">TensorFlow (Deprecated)</td>
5252
<td>FP32</td>
5353
<td>FP32</td>
5454
</tr>

docs/source/framework_yaml.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -25,9 +25,9 @@ unless they have clear requirements that can only be met by modifying the attrib
2525

2626
| Framework | YAML Configuration Files |
2727
|------------|:------------------------:|
28-
| TensorFlow | &#10004; |
28+
| TensorFlow (Deprecated) | &#10004; |
2929
| PyTorch | &#10004; |
30-
| ONNX | &#10004; |
30+
| ONNX (Deprecated) | &#10004; |
3131

3232

3333
## Get started with Framework YAML Files

docs/source/infrastructure.md

Lines changed: 7 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -34,11 +34,11 @@ Intel® Neural Compressor has unified interfaces which dispatch tasks to differe
3434
<td align="center"><a href="https://pytorch.org/docs/stable/quantization.html#eager-mode-quantization">PyTorch Eager</a>/<a href="https://pytorch.org/docs/stable/quantization.html#prototype-fx-graph-mode-quantization">PyTorch FX</a>/<a href="https://github.com/intel/intel-extension-for-pytorch">IPEX</a></td>
3535
</tr>
3636
<tr>
37-
<td align="center">TensorFlow</td>
37+
<td align="center">TensorFlow (Deprecated)</td>
3838
<td align="center"><a href="https://github.com/tensorflow/tensorflow">TensorFlow</a>/<a href="https://github.com/Intel-tensorflow/tensorflow">Intel TensorFlow</a></td>
3939
</tr>
4040
<tr>
41-
<td align="center">ONNX Runtime</td>
41+
<td align="center">ONNX Runtime (Deprecated)</td>
4242
<td align="center"><a href="https://github.com/microsoft/onnxruntime/blob/master/onnxruntime/python/tools/quantization/quantize.py">QLinearops/QDQ</a></td>
4343
</tr>
4444
<tr>
@@ -47,7 +47,7 @@ Intel® Neural Compressor has unified interfaces which dispatch tasks to differe
4747
<td align="center"><a href="https://pytorch.org/docs/stable/quantization.html#eager-mode-quantization">PyTorch eager mode</a>/<a href="https://pytorch.org/docs/stable/quantization.html#prototype-fx-graph-mode-quantization">PyTorch fx mode</a>/<a href="https://github.com/intel/intel-extension-for-pytorch">IPEX</a></td>
4848
</tr>
4949
<tr>
50-
<td align="center">ONNX Runtime</td>
50+
<td align="center">ONNX Runtime (Deprecated)</td>
5151
<td align="center"><a href="https://github.com/microsoft/onnxruntime/blob/master/onnxruntime/python/tools/quantization/quantize.py">QIntegerops</a></td>
5252
</tr>
5353
<tr>
@@ -56,7 +56,7 @@ Intel® Neural Compressor has unified interfaces which dispatch tasks to differe
5656
<td align="center"><a href="https://pytorch.org/docs/stable/quantization.html#eager-mode-quantization">PyTorch eager mode</a>/<a href="https://pytorch.org/docs/stable/quantization.html#prototype-fx-graph-mode-quantization">PyTorch fx mode</a>/<a href="https://github.com/intel/intel-extension-for-pytorch">IPEX</a></td>
5757
</tr>
5858
<tr>
59-
<td align="center">TensorFlow</td>
59+
<td align="center">TensorFlow (Deprecated)</td>
6060
<td align="center"><a href="https://github.com/tensorflow/tensorflow">TensorFlow</a>/<a href="https://github.com/Intel-tensorflow/tensorflow">Intel TensorFlow</a></td>
6161
</tr>
6262
</tbody>
@@ -79,7 +79,7 @@ Intel® Neural Compressor has unified interfaces which dispatch tasks to differe
7979
<td rowspan="3">Unstructured Pruning</td>
8080
<td rowspan="3">Element-wise</td>
8181
<td>Magnitude</td>
82-
<td>PyTorch, TensorFlow</td>
82+
<td>PyTorch, TensorFlow (Deprecated)</td>
8383
</tr>
8484
<tr>
8585
<td>Pattern Lock</td>
@@ -185,6 +185,6 @@ Intel® Neural Compressor has unified interfaces which dispatch tasks to differe
185185
[Mixed precision](mixed_precision.md):
186186
|Framework | |
187187
|--------------|:-----------:|
188-
|TensorFlow |&#10004; |
188+
|TensorFlow (Deprecated) |&#10004; |
189189
|PyTorch |&#10004; |
190-
|ONNX |plan to support in the future |
190+
|ONNX (Deprecated) |plan to support in the future |

docs/source/metric.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -3,11 +3,11 @@ Metrics
33
1. [Introduction](#introduction)
44
2. [Supported Built-in Metric Matrix](#supported-built-in-metric-matrix)
55

6-
2.1. [TensorFlow](#tensorflow)
6+
2.1. [TensorFlow (Deprecated)](#tensorflow)
77

88
2.2. [PyTorch](#pytorch)
99

10-
2.3. [ONNXRT](#onnxrt)
10+
2.3. [ONNXRT (Deprecated)](#onnxrt)
1111

1212
3. [Get Started with Metric](#get-started-with-metric)
1313

docs/source/mixed_precision.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -49,7 +49,7 @@ The recently launched 3rd Gen Intel® Xeon® Scalable processor (codenamed Coope
4949
<td align="left">:x:</td>
5050
</tr>
5151
<tr>
52-
<td rowspan="4" align="left">ONNX Runtime</td>
52+
<td rowspan="4" align="left">ONNX Runtime (Deprecated)</td>
5353
<td align="left">CPUExecutionProvider</td>
5454
<td align="left">MLAS</td>
5555
<td align="left">"default"</td>
@@ -82,7 +82,7 @@ The recently launched 3rd Gen Intel® Xeon® Scalable processor (codenamed Coope
8282
<td align="left">:x:</td>
8383
</tr>
8484
<tr>
85-
<td rowspan="2" align="left">Tensorflow</td>
85+
<td rowspan="2" align="left">Tensorflow (Deprecated)</td>
8686
<td align="left">Tensorflow</td>
8787
<td align="left">OneDNN</td>
8888
<td align="left">"default"</td>

0 commit comments

Comments
 (0)